Models

QAD-llama3.1-8B-iter4-fft

Diksha-VLLM-llama3.1-lora-V3

II-Tulu-8B-DPO

comm3_2

teaching3

Mixtral_AI_CyberCoder_7b

Synctalk_finetune_testing

llamademo

NPO-WMDP-llama3-8b-instruct

EYE-Llama_qa

PA-RAG_Llama-2-7b-chat-hf

zephyr-7b-sft-full

Llama-3-8B-dutch

MicroThinker-8B-Preview

OpenThinker-7B-abliterated

Qwen3-8B-medical-reasoning

seta-rl-qwen3-8b

RubricRM-8B-Judge-v2

aegisconduct

Llama-3.3-8B-Instruct-Thinking-Claude-Haiku-4.5-High-Reasoning-1700x

qwen3-8b-ncert-finetuned

Nemotron-Orchestrator-8B-mlx-fp16

TIM-8b-preview

Lyrical_Llama31_8B_ru2en_SFT

WangchanLION-v3

Kimi-K2T-neulab-agenttuning-webshop-sandboxes-maxeps-32k

exp-gfi-staqc-embedding-mean-filtered-10K_glm_4_7_traces_jupiter

Foundation-Sec-8B-Instruct-mlx-fp16

Tool-Genesis-Qwen3-8B-SFT

Mistral-3-7B_phrase

Mistral-3-7B_long

Llama-3.1-8B-code-ablation-exp1-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0002500

Qwen3-8B-SOCIALIQA-DPO

Llama-3.1-Med-Lite

gemma-2-9b_safety

StepORLM-Qwen3-8B

gemma-2-9b-it_multilingual

fixed-model

Qwen3-8B-FengGe-SFT

math-custom-data

GraphWalker-7B

Qwen3-8B-base-Open-R1-GRPO_dapo_acc_16384_nokl